Systems and methods for orthopedic implants
A system and computer-implemented method for manufacturing an orthopedic implant involves segmenting features in an image of anatomy. Anatomic elements can be isolated. Spatial relationships between the isolated anatomic elements can be manipulated. Negative space between anatomic elements is mapped before and/or after manipulating the spatial relationships. At least a portion of the negative space can be filled with a virtual implant. The virtual implant can be used to design and manufacture a physical implant.
1. A computer-implemented method for providing surgical assistance, the method comprising:
receiving one or more pre-operative images of a patient;
determining a patient-specific treatment plan for the patient, wherein the patient-specific treatment plan is determined at least in part by using at least one trained machine learning model, and wherein the patient-specific treatment plan includes:
a virtual model of a corrected spine of the patient based on the one or more pre-operative images of the patient, and
a patient-specific implant design for the patient-specific treatment plan;
after the patient-specific implant is implanted in the patient,
receiving one or more post-operative images of the patient,
determining a treatment outcome based on the received one or more post-operative images and the planned treatment, and
determining whether to retrain the at least one trained machine learning model based on the treatment outcome;
in response to determining to retrain the at least one trained machine learning model, selecting post-operative data of the patient as one or more training items;
retraining the at least one trained machine learning model using the one or more training items; and
determining, at least in part using the retrained at least one trained machine learning model, at least one patient-specific treatment plan for another patient.
2. The computer-implemented method of claim 1 , wherein retraining of the at least one trained machine learning model is based on a similarity score between a modeled result for the planned treatment and an actual post-operative result of the patient.
3. The computer-implemented method of claim 1 , wherein the patient-specific implant is a cage, a rod, a plate, or a spinal fusion device.
4. The computer-implemented method of claim 1 , further comprising generating a surgical plan that includes at least one annotated corrected anatomy image with insertion points and angles for the patient-specific implant.
5. The computer-implemented method of claim 1 , further comprising generating one or more images, viewable on a user device, of the virtual model, wherein the virtual model is a 3D model.
6. The computer-implemented method of claim 1 , wherein the virtual model is a 3D model with individually movable anatomical elements representing anatomical elements of the patient.
7. The computer-implemented method of claim 1 , wherein the post-operative data of the patient includes the one or more post-operative images of the patient.
8. The computer-implemented method of claim 1 , further comprising:
receiving post-operative data of the patient including at least one of a set of post-operative images of the patient, physician feedback, patient recovery level, recovery time, or result after a period of time; and
comparing at least a portion of the post-operative data of the patient to predicted data of the planned treatment, wherein selection of the post-operative data of the patient as the one or more training items is based on the comparison.
9. The computer-implemented method of claim 1 , further comprising generating a graphical user interface (GUI) displayable via a user device, wherein the GUI is configured to:
display, via the user device, one or more design parameters adjustable, via the GUI, to adjust one or more treatment simulations;
concurrently display, via the user device, at least one pre-operative image of the patient and at least one planned correction image of the patient; and
concurrently display, via the user device, pre-operative spinal parameters and planned spinal parameters for the patient.
10. The computer-implemented method of claim 1 , further comprising:
receiving post-operative data of the patient; and
determining spinal metrics for comparing a pre-operative anatomical configuration of the patient, a planned pathology of the patient, and post-operative anatomical configuration of the patient.
11. The computer-implemented method of claim 10 , wherein the spinal metrics include a plurality of pre-operative metrics and a plurality of planned metrics.
12. The computer-implemented method of claim 1 , further comprising:
obtaining at least one case selection parameter;
identifying a set of other patient cases from a plurality of other patient cases stored by a database based on the at least one case selection parameter; and
generating an interactive plan having outcome data for the planned treatment.
13. A computer-implemented method for training at least one trained machine learning model, the method comprising:
receiving one or more pre-operative digital images of a patient;
determining a surgery outcome for the patient in which an implant has been implanted, wherein the surgery outcome is based on the received one or more pre-operative digital images, a pre-operative surgical plan for the patient, and post-operative surgical data of the patient; and
in response to the surgery outcome meeting at least one training criterion,
inputting at least one of the pre-operative digital images as a training item into at least one trained machine learning model, wherein the at least one trained machine learning model retrained using the at least one of the post-operative digital images is configured to at least one of
determine a planned anatomical correction for another patient, or
design a patient-specific implant for another patient to achieve the planned anatomical correction.
14. The computer-implemented method of claim 13 , wherein the surgery outcome indicates a level of similarly between a model result and a post-operative result of the patient.
15. The computer-implemented method of claim 13 , further comprising comparing a model result for the pre-operative surgical plan to an actual post-operative result of the patient.
16. The computer-implemented method of claim 13 , further comprising inputting additional training items into the at least one trained machine learning model, wherein the additional training items include at least one of
an implant configuration of the patient-specific implant, or
a scored surgery outcome for the patient.
17. The computer-implemented method of claim 13 , further comprising:
generating, via a surgical plan platform, at least one of
a set of pre-corrective pathologic anatomy metrics for the patient, or
a corrected virtual model and set of post-corrections corrected anatomy metrics for the patient.
18. The computer-implemented method of claim 13 , further comprising:
generating, via a surgical plan platform, a displayable visual comparison of a pathology virtual model of the patient and a planned corrected virtual model of the patient.
19. The computer-implemented method of claim 18 ,
identifying, using a computer system, one or more implant locations along the pathology virtual model; and
generating displayable images with identified implant locations along the planned corrected virtual model representing a planned orthopedic correction.
20. A system comprising:
one or more processors; and
one or more memories storing instructions that, when executed by the one or more processors, cause the system to perform a process for training at least one trained machine learning model, the process comprising:
receiving one or more pre-operative digital images of a patient;
determining a surgery outcome for the patient in which an implant has been implanted, wherein the surgery outcome is based on the received one or more pre-operative digital images, a pre-operative surgical plan for the patient, and post-operative surgical data of the patient; and
in response to the surgery outcome meeting at least one training criterion,
inputting at least one of the pre-operative digital images as a training item into at least one trained machine learning model, wherein the at least one trained machine learning model retrained using the at least one of the post-operative digital images is configured to at least one of
determine a planned anatomical correction for another patient, or
design a patient-specific implant for another patient to achieve the planned anatomical correction.
21. The system of claim 20 , wherein the surgery outcome indicates a level of similarly between a model result and a post-operative result of the patient.
22. The system of claim 20 , wherein the process further comprises:
comparing a model result for the pre-operative surgical plan to an actual post-operative result of the patient.
23. The system of claim 20 , wherein the process further comprises:
inputting additional training items into the at least one trained machine learning model, wherein the additional training items include at least one of
an implant configuration of the patient-specific implant, or
a scored surgery outcome for the patient.
24. The system of claim 20 , wherein the process further comprises:
generating, via a surgical plan platform, at least one of
a set of pre-corrective pathologic anatomy metrics for the patient, or
a corrected virtual model and set of post-corrections corrected anatomy metrics for the patient.
25. The system of claim 20 , wherein the process further comprises:
generating, via a surgical plan platform, a displayable visual comparison of a pathology virtual model of the patient and a planned corrected virtual model of the patient.
26. A non-transitory computer-readable medium storing instructions that, when executed by a computing system, cause the computing system to perform operations for training at least one trained machine learning model, the operations comprising:
receiving one or more pre-operative digital images of a patient;
determining a surgery outcome for the patient in which an implant has been implanted, wherein the surgery outcome is based on the received one or more pre-operative digital images, a pre-operative surgical plan for the patient, and post-operative surgical data of the patient; and
in response to the surgery outcome meeting at least one training criterion,
inputting at least one of the pre-operative digital images as a training item into at least one trained machine learning model, wherein the at least one trained machine learning model retrained using the at least one of the post-operative digital images is configured to at least one of
determine a planned anatomical correction for another patient, or
design a patient-specific implant for another patient to achieve the planned anatomical correction.
27. The non-transitory computer-readable medium of claim 26 , wherein the surgery outcome indicates a level of similarly between a model result and a post-operative result of the patient.
28. The non-transitory computer-readable medium of claim 26 , wherein the operations further comprise:
comparing a model result for the pre-operative surgical plan to an actual post-operative result of the patient.
29. The non-transitory computer-readable medium of claim 26 , wherein the operations further comprise:
inputting additional training items into the at least one trained machine learning model, wherein the additional training items include at least one of
an implant configuration of the patient-specific implant, or
a scored surgery outcome for the patient.
30. The non-transitory computer-readable medium of claim 26 , wherein the operations further comprise:
generating, via a surgical plan platform, at least one of
a set of pre-corrective pathologic anatomy metrics for the patient, or
a corrected virtual model and set of post-corrections corrected anatomy metrics for the patient.